持續性遞迴世界賦能自主軟體演化

摘要

複雜軟體系統的開發時間跨度往往超過任何單一編碼智能體的生命週期。多數智能體軟體系統透過持久化會話、記憶、管理器或共享上下文來維持連續性。我們提出 EvoX Genesis（以下簡稱 Genesis），其做法相反——讓軟體專案保持持久，而本地智能體則維持有限生命週期。Genesis 將軟體表示為一個持久的遞迴世界：每個本地世界由已接受的版本與儲存庫路徑所定位，有限生命週期的智能體提出本地變更，遞迴委派將工作跨路徑移動，唯有被接受的結果才能推進持久的版本歷史。我們在形成、延續與再開發三個階段評估此組織方式。從一個沒有編譯器實作的儲存庫出發，Genesis 使用 DeepSeek V4 Flash 建構了一個約 25 萬行追蹤程式碼的 Rust 語言 C 編譯器；整個運行歷時超過 120 小時，歸檔了 1,000 多個智能體回合，而模型代幣費用僅花費 44 美元。該編譯器通過了完整的 c-testsuite 以及大部分 LLVM 和 Csmith 測試。在另一個使用 GLM 5.2 生成的獨立編譯器世界中，開發在反覆更換智能體後仍持續進行，同時完整保留測試表現。Genesis 也將 13 個 MESA 模組（超過 10 萬行 Fortran 程式碼）重新實作為一個接近 9 萬行 Rust 程式碼的 Rust 工作區；在六個數值工作負載中，達到了 1.55 至 6.87 倍的中位數加速。這些結果表明，長時程軟體開發可以圍繞持久化的專案來組織，而非依賴持久化的智能體。

English

Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents software as a persistent recursive world: each local world is situated by an accepted version and a repository path, finite-lived agents propose local changes, recursive delegation moves work across paths, and only accepted consequences advance the persistent version history. We evaluate this organization across formation, continuation and redevelopment. Starting from a repository with no compiler implementation, Genesis used DeepSeek V4 Flash to build a Rust-based C compiler with about 250k tracked lines; the run lasted over 120 hours, archived over 1,000 agent episodes and incurred only US$44 in model-token charges. The compiler passed the complete c-testsuite and most LLVM and Csmith tests. In a separate compiler world generated with GLM 5.2, development continued after repeated agent replacement while retaining full test performance. Genesis also reimplemented 13 MESA modules with over 100k Fortran lines as a Rust workspace with nearly 90k Rust lines; across six numerical workloads, it achieved median speedups of 1.55--6.87x. These results show that long-horizon software development can be organized around a persistent project rather than a persistent agent.